案例记录 case-run-00092

运行 #14/monthly_mom_growth

月收入环比增长

输出 2025 年每月收入及环比百分比 month、monthly_revenue、mom_pct，首月为 NULL，其余四舍五入 2 位，按 month 升序；必须使用 LAG。

运行信息

以下字段来自本次运行的冻结记录。

run#14

case run#92

attempt1

statuscompleted

token total19,540

estimated cost不可估算

model generation未记录

SQL execution228ms

adaptercodex_cli

response modetext

requested modelgpt-5.6-sol

resolved modelgpt-5.6-sol

provider request id未提供

started2026年8月29日 19:55

finished2026年8月29日 19:55

suite hash0a4a18b4374f510f5eff18b06272c30c3375e1f082ae405adc8ead7dd9c81556

模型输入

显示本次实际保存的完整 Prompt。

你是 Text-to-SQL 生成器。只生成完成问题所需的 SQL 和简短可见摘要，不输出隐藏推理。

方言与安全规则：
Use DuckDB SQL. Return exactly one read-only query. Do not access files, URLs, extensions, or schemas outside the supplied tables.

数据库结构：
{"semantic_relationships":[{"cardinality":"many_to_one","from_entity":"order","sql_on":"fact_orders.customer_id = dim_customers.customer_id","to_entity":"customer"},{"cardinality":"many_to_one","from_entity":"order","sql_on":"fact_orders.channel_id = dim_channels.channel_id","to_entity":"channel"},{"cardinality":"many_to_one","from_entity":"order_item","sql_on":"fact_order_items.order_id = fact_orders.order_id","to_entity":"order"},{"cardinality":"many_to_one","from_entity":"order_item","sql_on":"fact_order_items.product_id = dim_products.product_id","to_entity":"product"},{"cardinality":"many_to_one","from_entity":"payment","sql_on":"fact_payments.order_id = fact_orders.order_id","to_entity":"order"},{"cardinality":"many_to_one","from_entity":"return","sql_on":"fact_returns.order_id = fact_order_items.order_id AND fact_returns.line_no = fact_order_items.line_no","to_entity":"order_item"}],"tables":[{"columns":[{"data_type":"BIGINT","name":"channel_id","nullable":false},{"data_type":"VARCHAR","name":"channel_name","nullable":false},{"data_type":"VARCHAR","name":"channel_type","nullable":false}],"foreign_keys":[],"name":"dim_channels","primary_key":["channel_id"]},{"columns":[{"data_type":"BIGINT","name":"customer_id","nullable":false},{"data_type":"VARCHAR","name":"customer_name","nullable":false},{"data_type":"VARCHAR","name":"city","nullable":true},{"data_type":"DATE","name":"signup_date","nullable":false},{"data_type":"VARCHAR","name":"segment","nullable":false}],"foreign_keys":[],"name":"dim_customers","primary_key":["customer_id"]},{"columns":[{"data_type":"BIGINT","name":"product_id","nullable":false},{"data_type":"VARCHAR","name":"product_name","nullable":false},{"data_type":"VARCHAR","name":"category","nullable":false},{"data_type":"VARCHAR","name":"brand","nullable":false},{"data_type":"DECIMAL(14,2)","name":"list_price","nullable":false}],"foreign_keys":[],"name":"dim_products","primary_key":["product_id"]},{"columns":[{"data_type":"BIGINT","name":"order_id","nullable":false},{"data_type":"BIGINT","name":"line_no","nullable":false},{"data_type":"BIGINT","name":"product_id","nullable":false},{"data_type":"BIGINT","name":"quantity","nullable":false},{"data_type":"DECIMAL(14,2)","name":"unit_price","nullable":false},{"data_type":"DECIMAL(14,2)","name":"discount_amount","nullable":false}],"foreign_keys":[{"columns":["order_id"],"referenced_columns":["order_id"],"referenced_table":"fact_orders"},{"columns":["product_id"],"referenced_columns":["product_id"],"referenced_table":"dim_products"}],"name":"fact_order_items","primary_key":["order_id","line_no"]},{"columns":[{"data_type":"BIGINT","name":"order_id","nullable":false},{"data_type":"BIGINT","name":"customer_id","nullable":false},{"data_type":"BIGINT","name":"channel_id","nullable":false},{"data_type":"DATE","name":"order_date","nullable":false},{"data_type":"VARCHAR","name":"status","nullable":false},{"data_type":"DECIMAL(14,2)","name":"total_amount","nullable":false}],"foreign_keys":[{"columns":["customer_id"],"referenced_columns":["customer_id"],"referenced_table":"dim_customers"},{"columns":["channel_id"],"referenced_columns":["channel_id"],"referenced_table":"dim_channels"}],"name":"fact_orders","primary_key":["order_id"]},{"columns":[{"data_type":"BIGINT","name":"payment_id","nullable":false},{"data_type":"BIGINT","name":"order_id","nullable":false},{"data_type":"TIMESTAMP","name":"paid_at","nullable":false},{"data_type":"VARCHAR","name":"payment_method","nullable":false},{"data_type":"DECIMAL(14,2)","name":"amount","nullable":false},{"data_type":"VARCHAR","name":"status","nullable":false}],"foreign_keys":[{"columns":["order_id"],"referenced_columns":["order_id"],"referenced_table":"fact_orders"}],"name":"fact_payments","primary_key":["payment_id"]},{"columns":[{"data_type":"BIGINT","name":"return_id","nullable":false},{"data_type":"BIGINT","name":"order_id","nullable":false},{"data_type":"BIGINT","name":"line_no","nullable":false},{"data_type":"TIMESTAMP","name":"returned_at","nullable":false},{"data_type":"BIGINT","name":"return_qty","nullable":false},{"data_type":"DECIMAL(14,2)","name":"refund_amount","nullable":false},{"data_type":"VARCHAR","name":"reason","nullable":true}],"foreign_keys":[{"columns":["order_id","line_no"],"referenced_columns":["order_id","line_no"],"referenced_table":"fact_order_items"}],"name":"fact_returns","primary_key":["return_id"]}]}

语义层与业务口径：
{"business_rules":["完成订单仅指 fact_orders.status = 'completed'。","净销售额为 quantity * unit_price - discount_amount。","paid、refunded、failed 金额只按 fact_payments.status 分类。","退货率为完成订单的 returned_qty / sold_qty，售出数量仅含完成订单。","月份按 UTC Gregorian calendar 计算。"],"dimensions":[{"data_type":"VARCHAR","description":"客户分群","expression":"dim_customers.segment","name":"customer_segment"},{"data_type":"VARCHAR","description":"商品品类","expression":"dim_products.category","name":"product_category"},{"data_type":"VARCHAR","description":"渠道类型","expression":"dim_channels.channel_type","name":"channel_type"},{"data_type":"VARCHAR","description":"UTC Gregorian 月份","expression":"strftime(fact_orders.order_date, '%Y-%m')","name":"order_month"}],"entities":[{"description":"客户主数据","grain":"每行一个客户","name":"customer","primary_key":["customer_id"],"table":"dim_customers"},{"description":"商品主数据","grain":"每行一个商品","name":"product","primary_key":["product_id"],"table":"dim_products"},{"description":"渠道主数据","grain":"每行一个渠道","name":"channel","primary_key":["channel_id"],"table":"dim_channels"},{"description":"订单头","grain":"每行一个订单","name":"order","primary_key":["order_id"],"table":"fact_orders"},{"description":"订单行","grain":"每行一个订单商品行","name":"order_item","primary_key":["order_id","line_no"],"table":"fact_order_items"},{"description":"支付尝试","grain":"每行一笔支付","name":"payment","primary_key":["payment_id"],"table":"fact_payments"},{"description":"退货记录","grain":"每行一条订单行退货","name":"return","primary_key":["return_id"],"table":"fact_returns"}],"metrics":[{"description":"已完成订单数","expression":"COUNT(DISTINCT CASE WHEN fact_orders.status = 'completed' THEN fact_orders.order_id END)","filters":["fact_orders.status = 'completed'"],"grain":"聚合","name":"completed_order_count"},{"description":"完成订单商品行净销售额","expression":"SUM(fact_order_items.quantity * fact_order_items.unit_price - fact_order_items.discount_amount)","filters":["fact_orders.status = 'completed'"],"grain":"聚合","name":"net_revenue"},{"description":"成功支付金额","expression":"SUM(CASE WHEN fact_payments.status = 'paid' THEN fact_payments.amount ELSE 0 END)","filters":[],"grain":"聚合","name":"paid_amount"},{"description":"退款状态支付金额","expression":"SUM(CASE WHEN fact_payments.status = 'refunded' THEN fact_payments.amount ELSE 0 END)","filters":[],"grain":"聚合","name":"refunded_amount"},{"description":"失败支付金额","expression":"SUM(CASE WHEN fact_payments.status = 'failed' THEN fact_payments.amount ELSE 0 END)","filters":[],"grain":"聚合","name":"failed_amount"},{"description":"完成订单退货数量除以售出数量","expression":"SUM(fact_returns.return_qty) / SUM(fact_order_items.quantity)","filters":["fact_orders.status = 'completed'"],"grain":"聚合","name":"return_rate"}],"relationships":[{"cardinality":"many_to_one","from_entity":"order","sql_on":"fact_orders.customer_id = dim_customers.customer_id","to_entity":"customer"},{"cardinality":"many_to_one","from_entity":"order","sql_on":"fact_orders.channel_id = dim_channels.channel_id","to_entity":"channel"},{"cardinality":"many_to_one","from_entity":"order_item","sql_on":"fact_order_items.order_id = fact_orders.order_id","to_entity":"order"},{"cardinality":"many_to_one","from_entity":"order_item","sql_on":"fact_order_items.product_id = dim_products.product_id","to_entity":"product"},{"cardinality":"many_to_one","from_entity":"payment","sql_on":"fact_payments.order_id = fact_orders.order_id","to_entity":"order"},{"cardinality":"many_to_one","from_entity":"return","sql_on":"fact_returns.order_id = fact_order_items.order_id AND fact_returns.line_no = fact_order_items.line_no","to_entity":"order_item"}]}

问题：
输出 2025 年每月收入及环比百分比 month、monthly_revenue、mom_pct，首月为 NULL，其余四舍五入 2 位，按 month 升序；必须使用 LAG。

输出必须严格匹配此 JSON Schema：
{"additionalProperties":false,"properties":{"assumptions":{"items":{"type":"string"},"title":"Assumptions","type":"array"},"sql":{"title":"Sql","type":"string"},"summary":{"title":"Summary","type":"string"}},"required":["sql","summary","assumptions"],"title":"GenerationOutput","type":"object"}

调用请求（1）

按事件序号排列；密钥和 Authorization 已移除。

历史证据边界：完整 Prompt 已保存，但这次 codex_cli 记录没有保存底层 HTTP 报文或 CLI 参数。本站不会把推测内容伪装成原始请求；未来运行会在 provider.requested 中记录脱敏后的完整调用信封。

请求 #1SEQ 542026年8月29日 11:55:33 UTC

{
  "isolation_policy_hash": "9f063cf8adc7f2032be9534f558cf2fd3c1d945ec051975e64dfd1651ef367ff",
  "status": "running"
}

模型输出

分别显示原始响应、解析结果和 SQL。

原始响应 raw_output

{"sql":"WITH monthly AS (\n    SELECT\n        strftime(o.order_date, '%Y-%m') AS month,\n        SUM(oi.quantity * oi.unit_price - oi.discount_amount) AS monthly_revenue\n    FROM fact_orders AS o\n    JOIN fact_order_items AS oi\n      ON oi.order_id = o.order_id\n    WHERE o.status = 'completed'\n      AND o.order_date >= DATE '2025-01-01'\n      AND o.order_date < DATE '2026-01-01'\n    GROUP BY 1\n), with_previous AS (\n    SELECT\n        month,\n        monthly_revenue,\n        LAG(monthly_revenue) OVER (ORDER BY month) AS previous_revenue\n    FROM monthly\n)\nSELECT\n    month,\n    monthly_revenue,\n    ROUND(\n        100.0 * (monthly_revenue - previous_revenue)\n        / NULLIF(previous_revenue, 0),\n        2\n    ) AS mom_pct\nFROM with_previous\nORDER BY month ASC;","summary":"按月汇总 2025 年完成订单的净销售额，并使用 LAG 计算环比百分比；首个有收入月份为 NULL。","assumptions":["仅输出 2025 年存在完成订单商品行的月份，不补齐无数据月份。","收入采用语义层定义的净销售额：quantity * unit_price - discount_amount。","若上月收入为 0，则该月 mom_pct 返回 NULL，以避免除零。"]}

结构化查询方案 plan

没有可解析方案。

模型生成 SQL

WITH monthly AS (
    SELECT
        strftime(o.order_date, '%Y-%m') AS month,
        SUM(oi.quantity * oi.unit_price - oi.discount_amount) AS monthly_revenue
    FROM fact_orders AS o
    JOIN fact_order_items AS oi
      ON oi.order_id = o.order_id
    WHERE o.status = 'completed'
      AND o.order_date >= DATE '2025-01-01'
      AND o.order_date < DATE '2026-01-01'
    GROUP BY 1
), with_previous AS (
    SELECT
        month,
        monthly_revenue,
        LAG(monthly_revenue) OVER (ORDER BY month) AS previous_revenue
    FROM monthly
)
SELECT
    month,
    monthly_revenue,
    ROUND(
        100.0 * (monthly_revenue - previous_revenue)
        / NULLIF(previous_revenue, 0),
        2
    ) AS mom_pct
FROM with_previous
ORDER BY month ASC;

规范化 SQL

WITH monthly AS (
  SELECT
    STRFTIME(o.order_date, '%Y-%m') AS month,
    SUM(oi.quantity * oi.unit_price - oi.discount_amount) AS monthly_revenue
  FROM fact_orders AS o
  JOIN fact_order_items AS oi
    ON oi.order_id = o.order_id
  WHERE
    o.status = 'completed'
    AND o.order_date >= CAST('2025-01-01' AS DATE)
    AND o.order_date < CAST('2026-01-01' AS DATE)
  GROUP BY
    1
), with_previous AS (
  SELECT
    month,
    monthly_revenue,
    LAG(monthly_revenue) OVER (ORDER BY month) AS previous_revenue
  FROM monthly
)
SELECT
  month,
  monthly_revenue,
  ROUND(100.0 * (
    monthly_revenue - previous_revenue
  ) / NULLIF(previous_revenue, 0), 2) AS mom_pct
FROM with_previous
ORDER BY
  month ASC

Token 与耗时

{
  "token_usage": {
    "cache_write_input_tokens": 0,
    "cached_input_tokens": 0,
    "input_tokens": 19138,
    "output_tokens": 402,
    "reasoning_output_tokens": 61
  },
  "generation_ms": null,
  "execution_ms": 228.02033300104085
}

评分结果

包含评分明细、参考 SQL、结构要求、比较规则和结果差异。

评分明细 score

{
  "ast_rules": [
    {
      "details": {
        "actual": 1,
        "required": 1
      },
      "id": "mom-lag",
      "kind": "window_function",
      "passed": true
    }
  ],
  "column_count": 5,
  "column_names": 5,
  "execution": 10,
  "ordering": 10,
  "protocol": 5,
  "read_only_ast": 5,
  "row_f1": 45,
  "sql_capability": 15,
  "total": 100
}

参考 SQL

WITH monthly AS (SELECT strftime(order_date, '%Y-%m') AS month, SUM(total_amount) AS monthly_revenue FROM fact_orders WHERE status = 'completed' AND order_date >= DATE '2025-01-01' AND order_date < DATE '2026-01-01' GROUP BY month), lagged AS (SELECT month, monthly_revenue, LAG(monthly_revenue) OVER (ORDER BY month ASC) AS previous_revenue FROM monthly) SELECT month, monthly_revenue, ROUND((monthly_revenue - previous_revenue) / NULLIF(previous_revenue, 0) * 100, 2) AS mom_pct FROM lagged ORDER BY month ASC

AST 结构要求

[
  {
    "id": "mom-lag",
    "kind": "window_function",
    "min": 1,
    "name": "LAG",
    "order_by": [
      {
        "direction": "ASC",
        "expression": "month"
      }
    ],
    "partition_columns": []
  }
]

结果比较规则

{
  "abs_tolerance": "0.005",
  "decimal_scale": 2,
  "duplicate_policy": "multiset",
  "max_rows": 10000,
  "rel_tolerance": "0",
  "row_order_significant": true
}

期望结果预览

{
  "columns": [
    {
      "name": "month",
      "type": "VARCHAR"
    },
    {
      "name": "monthly_revenue",
      "type": "DECIMAL(38,2)"
    },
    {
      "name": "mom_pct",
      "type": "DOUBLE"
    }
  ],
  "digest": "fccf4e8346d7523eb82d754179d442eacaffefa2dc0c4dfd3de2bf71f5a99ec0",
  "row_count": 12,
  "rows": [
    [
      "2025-01",
      "41876.75",
      null
    ],
    [
      "2025-02",
      "31673.25",
      "-24.37"
    ],
    [
      "2025-03",
      "34373.25",
      "8.52"
    ],
    [
      "2025-04",
      "25069.00",
      "-27.07"
    ],
    [
      "2025-05",
      "30064.50",
      "19.93"
    ],
    [
      "2025-06",
      "31993.75",
      "6.42"
    ],
    [
      "2025-07",
      "36093.75",
      "12.82"
    ],
    [
      "2025-08",
      "29252.75",
      "-18.95"
    ],
    [
      "2025-09",
      "26246.25",
      "-10.28"
    ],
    [
      "2025-10",
      "21555.25",
      "-17.87"
    ],
    [
      "2025-11",
      "34944.25",
      "62.11"
    ],
    [
      "2025-12",
      "20373.00",
      "-41.7"
    ]
  ]
}

实际结果预览

{
  "columns": [
    {
      "name": "month",
      "type": "VARCHAR"
    },
    {
      "name": "monthly_revenue",
      "type": "DECIMAL(38,2)"
    },
    {
      "name": "mom_pct",
      "type": "DOUBLE"
    }
  ],
  "extra": [],
  "missing": [],
  "row_count": 12,
  "rows": [
    [
      "2025-01",
      "41876.75",
      null
    ],
    [
      "2025-02",
      "31673.25",
      -24.37
    ],
    [
      "2025-03",
      "34373.25",
      8.52
    ],
    [
      "2025-04",
      "25069.00",
      -27.07
    ],
    [
      "2025-05",
      "30064.50",
      19.93
    ],
    [
      "2025-06",
      "31993.75",
      6.42
    ],
    [
      "2025-07",
      "36093.75",
      12.82
    ],
    [
      "2025-08",
      "29252.75",
      -18.95
    ],
    [
      "2025-09",
      "26246.25",
      -10.28
    ],
    [
      "2025-10",
      "21555.25",
      -17.87
    ],
    [
      "2025-11",
      "34944.25",
      62.11
    ],
    [
      "2025-12",
      "20373.00",
      -41.7
    ]
  ]
}

摘要、错误与结果哈希

{
  "visible_summary": "按月汇总 2025 年完成订单的净销售额，并使用 LAG 计算环比百分比；首个有收入月份为 NULL。",
  "error_code": null,
  "error_message": null,
  "expected_digest": "fccf4e8346d7523eb82d754179d442eacaffefa2dc0c4dfd3de2bf71f5a99ec0",
  "actual_digest": "721ba5e54f56af1da456da0c6d8cbd3e3bc9e4ee240f91f7f0bcdd347940cae3",
  "assumptions": null
}

事件记录（7）

按全局事件序号排列，保留时间、级别、类型、消息和 payload。

SEQ 52case.startedinfo2026年8月29日 11:55:33 UTC

{
  "status": "generating"
}

SEQ 53prompt.builtinfo2026年8月29日 11:55:33 UTC

{
  "status": "completed"
}

SEQ 54provider.requestedinfo2026年8月29日 11:55:33 UTC

{
  "isolation_policy_hash": "9f063cf8adc7f2032be9534f558cf2fd3c1d945ec051975e64dfd1651ef367ff",
  "status": "running"
}

SEQ 55provider.deltainfo2026年8月29日 11:55:53 UTC

{
  "text": "{\"sql\":\"WITH monthly AS (\\n    SELECT\\n        strftime(o.order_date, '%Y-%m') AS month,\\n        SUM(oi.quantity * oi.unit_price - oi.discount_amount) AS monthly_revenue\\n    FROM fact_orders AS o\\n    JOIN fact_order_items AS oi\\n      ON oi.order_id = o.order_id\\n    WHERE o.status = 'completed'\\n      AND o.order_date >= DATE '2025-01-01'\\n      AND o.order_date < DATE '2026-01-01'\\n    GROUP BY 1\\n), with_previous AS (\\n    SELECT\\n        month,\\n        monthly_revenue,\\n        LAG(monthly_revenue) OVER (ORDER BY month) AS previous_revenue\\n    FROM monthly\\n)\\nSELECT\\n    month,\\n    monthly_revenue,\\n    ROUND(\\n        100.0 * (monthly_revenue - previous_revenue)\\n        / NULLIF(previous_revenue, 0),\\n        2\\n    ) AS mom_pct\\nFROM with_previous\\nORDER BY month ASC;\",\"summary\":\"按月汇总 2025 年完成订单的净销售额，并使用 LAG 计算环比百分比；首个有收入月份为 NULL。\",\"assumptions\":[\"仅输出 2025 年存在完成订单商品行的月份，不补齐无数据月份。\",\"收入采用语义层定义的净销售额：quantity * unit_price - discount_amount。\",\"若上月收入为 0，则该月 mom_pct 返回 NULL，以避免除零。\"]}"
}

SEQ 56provider.completedinfo2026年8月29日 11:55:53 UTC

{
  "elapsed_ms": 20293.861458998435,
  "status": "completed",
  "token_usage": {
    "cache_write_input_tokens": 0,
    "cached_input_tokens": 0,
    "input_tokens": 19138,
    "output_tokens": 402,
    "reasoning_output_tokens": 61
  }
}

SEQ 57sql.parsedinfo2026年8月29日 11:55:54 UTC

{
  "status": "completed"
}

SEQ 58score.completedinfo2026年8月29日 11:55:54 UTC

{
  "score": 100,
  "status": "completed"
}

原始案例数据

完整 JSON 字段，不经过页面裁剪。

展开全部原始字段

{
  "actual_digest": "721ba5e54f56af1da456da0c6d8cbd3e3bc9e4ee240f91f7f0bcdd347940cae3",
  "assumptions": null,
  "attempt": 1,
  "category": "window_offset",
  "comparison": {
    "abs_tolerance": "0.005",
    "decimal_scale": 2,
    "duplicate_policy": "multiset",
    "max_rows": 10000,
    "rel_tolerance": "0",
    "row_order_significant": true
  },
  "difficulty": "medium",
  "error_code": null,
  "error_message": null,
  "execution_ms": 228.02033300104085,
  "expected_digest": "fccf4e8346d7523eb82d754179d442eacaffefa2dc0c4dfd3de2bf71f5a99ec0",
  "expected_result_preview": {
    "columns": [
      {
        "name": "month",
        "type": "VARCHAR"
      },
      {
        "name": "monthly_revenue",
        "type": "DECIMAL(38,2)"
      },
      {
        "name": "mom_pct",
        "type": "DOUBLE"
      }
    ],
    "digest": "fccf4e8346d7523eb82d754179d442eacaffefa2dc0c4dfd3de2bf71f5a99ec0",
    "row_count": 12,
    "rows": [
      [
        "2025-01",
        "41876.75",
        null
      ],
      [
        "2025-02",
        "31673.25",
        "-24.37"
      ],
      [
        "2025-03",
        "34373.25",
        "8.52"
      ],
      [
        "2025-04",
        "25069.00",
        "-27.07"
      ],
      [
        "2025-05",
        "30064.50",
        "19.93"
      ],
      [
        "2025-06",
        "31993.75",
        "6.42"
      ],
      [
        "2025-07",
        "36093.75",
        "12.82"
      ],
      [
        "2025-08",
        "29252.75",
        "-18.95"
      ],
      [
        "2025-09",
        "26246.25",
        "-10.28"
      ],
      [
        "2025-10",
        "21555.25",
        "-17.87"
      ],
      [
        "2025-11",
        "34944.25",
        "62.11"
      ],
      [
        "2025-12",
        "20373.00",
        "-41.7"
      ]
    ]
  },
  "finished_at": "2026-08-29T19:55:54.236143",
  "formatted_sql": "WITH monthly AS (\n  SELECT\n    STRFTIME(o.order_date, '%Y-%m') AS month,\n    SUM(oi.quantity * oi.unit_price - oi.discount_amount) AS monthly_revenue\n  FROM fact_orders AS o\n  JOIN fact_order_items AS oi\n    ON oi.order_id = o.order_id\n  WHERE\n    o.status = 'completed'\n    AND o.order_date >= CAST('2025-01-01' AS DATE)\n    AND o.order_date < CAST('2026-01-01' AS DATE)\n  GROUP BY\n    1\n), with_previous AS (\n  SELECT\n    month,\n    monthly_revenue,\n    LAG(monthly_revenue) OVER (ORDER BY month) AS previous_revenue\n  FROM monthly\n)\nSELECT\n  month,\n  monthly_revenue,\n  ROUND(100.0 * (\n    monthly_revenue - previous_revenue\n  ) / NULLIF(previous_revenue, 0), 2) AS mom_pct\nFROM with_previous\nORDER BY\n  month ASC",
  "generated_sql": "WITH monthly AS (\n    SELECT\n        strftime(o.order_date, '%Y-%m') AS month,\n        SUM(oi.quantity * oi.unit_price - oi.discount_amount) AS monthly_revenue\n    FROM fact_orders AS o\n    JOIN fact_order_items AS oi\n      ON oi.order_id = o.order_id\n    WHERE o.status = 'completed'\n      AND o.order_date >= DATE '2025-01-01'\n      AND o.order_date < DATE '2026-01-01'\n    GROUP BY 1\n), with_previous AS (\n    SELECT\n        month,\n        monthly_revenue,\n        LAG(monthly_revenue) OVER (ORDER BY month) AS previous_revenue\n    FROM monthly\n)\nSELECT\n    month,\n    monthly_revenue,\n    ROUND(\n        100.0 * (monthly_revenue - previous_revenue)\n        / NULLIF(previous_revenue, 0),\n        2\n    ) AS mom_pct\nFROM with_previous\nORDER BY month ASC;",
  "generation_ms": null,
  "id": 92,
  "model_name": "Sol 本机实测",
  "model_run_id": 17,
  "plan": null,
  "prompt": "你是 Text-to-SQL 生成器。只生成完成问题所需的 SQL 和简短可见摘要，不输出隐藏推理。\n\n方言与安全规则：\nUse DuckDB SQL. Return exactly one read-only query. Do not access files, URLs, extensions, or schemas outside the supplied tables.\n\n数据库结构：\n{\"semantic_relationships\":[{\"cardinality\":\"many_to_one\",\"from_entity\":\"order\",\"sql_on\":\"fact_orders.customer_id = dim_customers.customer_id\",\"to_entity\":\"customer\"},{\"cardinality\":\"many_to_one\",\"from_entity\":\"order\",\"sql_on\":\"fact_orders.channel_id = dim_channels.channel_id\",\"to_entity\":\"channel\"},{\"cardinality\":\"many_to_one\",\"from_entity\":\"order_item\",\"sql_on\":\"fact_order_items.order_id = fact_orders.order_id\",\"to_entity\":\"order\"},{\"cardinality\":\"many_to_one\",\"from_entity\":\"order_item\",\"sql_on\":\"fact_order_items.product_id = dim_products.product_id\",\"to_entity\":\"product\"},{\"cardinality\":\"many_to_one\",\"from_entity\":\"payment\",\"sql_on\":\"fact_payments.order_id = fact_orders.order_id\",\"to_entity\":\"order\"},{\"cardinality\":\"many_to_one\",\"from_entity\":\"return\",\"sql_on\":\"fact_returns.order_id = fact_order_items.order_id AND fact_returns.line_no = fact_order_items.line_no\",\"to_entity\":\"order_item\"}],\"tables\":[{\"columns\":[{\"data_type\":\"BIGINT\",\"name\":\"channel_id\",\"nullable\":false},{\"data_type\":\"VARCHAR\",\"name\":\"channel_name\",\"nullable\":false},{\"data_type\":\"VARCHAR\",\"name\":\"channel_type\",\"nullable\":false}],\"foreign_keys\":[],\"name\":\"dim_channels\",\"primary_key\":[\"channel_id\"]},{\"columns\":[{\"data_type\":\"BIGINT\",\"name\":\"customer_id\",\"nullable\":false},{\"data_type\":\"VARCHAR\",\"name\":\"customer_name\",\"nullable\":false},{\"data_type\":\"VARCHAR\",\"name\":\"city\",\"nullable\":true},{\"data_type\":\"DATE\",\"name\":\"signup_date\",\"nullable\":false},{\"data_type\":\"VARCHAR\",\"name\":\"segment\",\"nullable\":false}],\"foreign_keys\":[],\"name\":\"dim_customers\",\"primary_key\":[\"customer_id\"]},{\"columns\":[{\"data_type\":\"BIGINT\",\"name\":\"product_id\",\"nullable\":false},{\"data_type\":\"VARCHAR\",\"name\":\"product_name\",\"nullable\":false},{\"data_type\":\"VARCHAR\",\"name\":\"category\",\"nullable\":false},{\"data_type\":\"VARCHAR\",\"name\":\"brand\",\"nullable\":false},{\"data_type\":\"DECIMAL(14,2)\",\"name\":\"list_price\",\"nullable\":false}],\"foreign_keys\":[],\"name\":\"dim_products\",\"primary_key\":[\"product_id\"]},{\"columns\":[{\"data_type\":\"BIGINT\",\"name\":\"order_id\",\"nullable\":false},{\"data_type\":\"BIGINT\",\"name\":\"line_no\",\"nullable\":false},{\"data_type\":\"BIGINT\",\"name\":\"product_id\",\"nullable\":false},{\"data_type\":\"BIGINT\",\"name\":\"quantity\",\"nullable\":false},{\"data_type\":\"DECIMAL(14,2)\",\"name\":\"unit_price\",\"nullable\":false},{\"data_type\":\"DECIMAL(14,2)\",\"name\":\"discount_amount\",\"nullable\":false}],\"foreign_keys\":[{\"columns\":[\"order_id\"],\"referenced_columns\":[\"order_id\"],\"referenced_table\":\"fact_orders\"},{\"columns\":[\"product_id\"],\"referenced_columns\":[\"product_id\"],\"referenced_table\":\"dim_products\"}],\"name\":\"fact_order_items\",\"primary_key\":[\"order_id\",\"line_no\"]},{\"columns\":[{\"data_type\":\"BIGINT\",\"name\":\"order_id\",\"nullable\":false},{\"data_type\":\"BIGINT\",\"name\":\"customer_id\",\"nullable\":false},{\"data_type\":\"BIGINT\",\"name\":\"channel_id\",\"nullable\":false},{\"data_type\":\"DATE\",\"name\":\"order_date\",\"nullable\":false},{\"data_type\":\"VARCHAR\",\"name\":\"status\",\"nullable\":false},{\"data_type\":\"DECIMAL(14,2)\",\"name\":\"total_amount\",\"nullable\":false}],\"foreign_keys\":[{\"columns\":[\"customer_id\"],\"referenced_columns\":[\"customer_id\"],\"referenced_table\":\"dim_customers\"},{\"columns\":[\"channel_id\"],\"referenced_columns\":[\"channel_id\"],\"referenced_table\":\"dim_channels\"}],\"name\":\"fact_orders\",\"primary_key\":[\"order_id\"]},{\"columns\":[{\"data_type\":\"BIGINT\",\"name\":\"payment_id\",\"nullable\":false},{\"data_type\":\"BIGINT\",\"name\":\"order_id\",\"nullable\":false},{\"data_type\":\"TIMESTAMP\",\"name\":\"paid_at\",\"nullable\":false},{\"data_type\":\"VARCHAR\",\"name\":\"payment_method\",\"nullable\":false},{\"data_type\":\"DECIMAL(14,2)\",\"name\":\"amount\",\"nullable\":false},{\"data_type\":\"VARCHAR\",\"name\":\"status\",\"nullable\":false}],\"foreign_keys\":[{\"columns\":[\"order_id\"],\"referenced_columns\":[\"order_id\"],\"referenced_table\":\"fact_orders\"}],\"name\":\"fact_payments\",\"primary_key\":[\"payment_id\"]},{\"columns\":[{\"data_type\":\"BIGINT\",\"name\":\"return_id\",\"nullable\":false},{\"data_type\":\"BIGINT\",\"name\":\"order_id\",\"nullable\":false},{\"data_type\":\"BIGINT\",\"name\":\"line_no\",\"nullable\":false},{\"data_type\":\"TIMESTAMP\",\"name\":\"returned_at\",\"nullable\":false},{\"data_type\":\"BIGINT\",\"name\":\"return_qty\",\"nullable\":false},{\"data_type\":\"DECIMAL(14,2)\",\"name\":\"refund_amount\",\"nullable\":false},{\"data_type\":\"VARCHAR\",\"name\":\"reason\",\"nullable\":true}],\"foreign_keys\":[{\"columns\":[\"order_id\",\"line_no\"],\"referenced_columns\":[\"order_id\",\"line_no\"],\"referenced_table\":\"fact_order_items\"}],\"name\":\"fact_returns\",\"primary_key\":[\"return_id\"]}]}\n\n语义层与业务口径：\n{\"business_rules\":[\"完成订单仅指 fact_orders.status = 'completed'。\",\"净销售额为 quantity * unit_price - discount_amount。\",\"paid、refunded、failed 金额只按 fact_payments.status 分类。\",\"退货率为完成订单的 returned_qty / sold_qty，售出数量仅含完成订单。\",\"月份按 UTC Gregorian calendar 计算。\"],\"dimensions\":[{\"data_type\":\"VARCHAR\",\"description\":\"客户分群\",\"expression\":\"dim_customers.segment\",\"name\":\"customer_segment\"},{\"data_type\":\"VARCHAR\",\"description\":\"商品品类\",\"expression\":\"dim_products.category\",\"name\":\"product_category\"},{\"data_type\":\"VARCHAR\",\"description\":\"渠道类型\",\"expression\":\"dim_channels.channel_type\",\"name\":\"channel_type\"},{\"data_type\":\"VARCHAR\",\"description\":\"UTC Gregorian 月份\",\"expression\":\"strftime(fact_orders.order_date, '%Y-%m')\",\"name\":\"order_month\"}],\"entities\":[{\"description\":\"客户主数据\",\"grain\":\"每行一个客户\",\"name\":\"customer\",\"primary_key\":[\"customer_id\"],\"table\":\"dim_customers\"},{\"description\":\"商品主数据\",\"grain\":\"每行一个商品\",\"name\":\"product\",\"primary_key\":[\"product_id\"],\"table\":\"dim_products\"},{\"description\":\"渠道主数据\",\"grain\":\"每行一个渠道\",\"name\":\"channel\",\"primary_key\":[\"channel_id\"],\"table\":\"dim_channels\"},{\"description\":\"订单头\",\"grain\":\"每行一个订单\",\"name\":\"order\",\"primary_key\":[\"order_id\"],\"table\":\"fact_orders\"},{\"description\":\"订单行\",\"grain\":\"每行一个订单商品行\",\"name\":\"order_item\",\"primary_key\":[\"order_id\",\"line_no\"],\"table\":\"fact_order_items\"},{\"description\":\"支付尝试\",\"grain\":\"每行一笔支付\",\"name\":\"payment\",\"primary_key\":[\"payment_id\"],\"table\":\"fact_payments\"},{\"description\":\"退货记录\",\"grain\":\"每行一条订单行退货\",\"name\":\"return\",\"primary_key\":[\"return_id\"],\"table\":\"fact_returns\"}],\"metrics\":[{\"description\":\"已完成订单数\",\"expression\":\"COUNT(DISTINCT CASE WHEN fact_orders.status = 'completed' THEN fact_orders.order_id END)\",\"filters\":[\"fact_orders.status = 'completed'\"],\"grain\":\"聚合\",\"name\":\"completed_order_count\"},{\"description\":\"完成订单商品行净销售额\",\"expression\":\"SUM(fact_order_items.quantity * fact_order_items.unit_price - fact_order_items.discount_amount)\",\"filters\":[\"fact_orders.status = 'completed'\"],\"grain\":\"聚合\",\"name\":\"net_revenue\"},{\"description\":\"成功支付金额\",\"expression\":\"SUM(CASE WHEN fact_payments.status = 'paid' THEN fact_payments.amount ELSE 0 END)\",\"filters\":[],\"grain\":\"聚合\",\"name\":\"paid_amount\"},{\"description\":\"退款状态支付金额\",\"expression\":\"SUM(CASE WHEN fact_payments.status = 'refunded' THEN fact_payments.amount ELSE 0 END)\",\"filters\":[],\"grain\":\"聚合\",\"name\":\"refunded_amount\"},{\"description\":\"失败支付金额\",\"expression\":\"SUM(CASE WHEN fact_payments.status = 'failed' THEN fact_payments.amount ELSE 0 END)\",\"filters\":[],\"grain\":\"聚合\",\"name\":\"failed_amount\"},{\"description\":\"完成订单退货数量除以售出数量\",\"expression\":\"SUM(fact_returns.return_qty) / SUM(fact_order_items.quantity)\",\"filters\":[\"fact_orders.status = 'completed'\"],\"grain\":\"聚合\",\"name\":\"return_rate\"}],\"relationships\":[{\"cardinality\":\"many_to_one\",\"from_entity\":\"order\",\"sql_on\":\"fact_orders.customer_id = dim_customers.customer_id\",\"to_entity\":\"customer\"},{\"cardinality\":\"many_to_one\",\"from_entity\":\"order\",\"sql_on\":\"fact_orders.channel_id = dim_channels.channel_id\",\"to_entity\":\"channel\"},{\"cardinality\":\"many_to_one\",\"from_entity\":\"order_item\",\"sql_on\":\"fact_order_items.order_id = fact_orders.order_id\",\"to_entity\":\"order\"},{\"cardinality\":\"many_to_one\",\"from_entity\":\"order_item\",\"sql_on\":\"fact_order_items.product_id = dim_products.product_id\",\"to_entity\":\"product\"},{\"cardinality\":\"many_to_one\",\"from_entity\":\"payment\",\"sql_on\":\"fact_payments.order_id = fact_orders.order_id\",\"to_entity\":\"order\"},{\"cardinality\":\"many_to_one\",\"from_entity\":\"return\",\"sql_on\":\"fact_returns.order_id = fact_order_items.order_id AND fact_returns.line_no = fact_order_items.line_no\",\"to_entity\":\"order_item\"}]}\n\n问题：\n输出 2025 年每月收入及环比百分比 month、monthly_revenue、mom_pct，首月为 NULL，其余四舍五入 2 位，按 month 升序；必须使用 LAG。\n\n输出必须严格匹配此 JSON Schema：\n{\"additionalProperties\":false,\"properties\":{\"assumptions\":{\"items\":{\"type\":\"string\"},\"title\":\"Assumptions\",\"type\":\"array\"},\"sql\":{\"title\":\"Sql\",\"type\":\"string\"},\"summary\":{\"title\":\"Summary\",\"type\":\"string\"}},\"required\":[\"sql\",\"summary\",\"assumptions\"],\"title\":\"GenerationOutput\",\"type\":\"object\"}",
  "provider_request_id": null,
  "question": "输出 2025 年每月收入及环比百分比 month、monthly_revenue、mom_pct，首月为 NULL，其余四舍五入 2 位，按 month 升序；必须使用 LAG。",
  "radar_dimension": "窗口函数",
  "raw_output": "{\"sql\":\"WITH monthly AS (\\n    SELECT\\n        strftime(o.order_date, '%Y-%m') AS month,\\n        SUM(oi.quantity * oi.unit_price - oi.discount_amount) AS monthly_revenue\\n    FROM fact_orders AS o\\n    JOIN fact_order_items AS oi\\n      ON oi.order_id = o.order_id\\n    WHERE o.status = 'completed'\\n      AND o.order_date >= DATE '2025-01-01'\\n      AND o.order_date < DATE '2026-01-01'\\n    GROUP BY 1\\n), with_previous AS (\\n    SELECT\\n        month,\\n        monthly_revenue,\\n        LAG(monthly_revenue) OVER (ORDER BY month) AS previous_revenue\\n    FROM monthly\\n)\\nSELECT\\n    month,\\n    monthly_revenue,\\n    ROUND(\\n        100.0 * (monthly_revenue - previous_revenue)\\n        / NULLIF(previous_revenue, 0),\\n        2\\n    ) AS mom_pct\\nFROM with_previous\\nORDER BY month ASC;\",\"summary\":\"按月汇总 2025 年完成订单的净销售额，并使用 LAG 计算环比百分比；首个有收入月份为 NULL。\",\"assumptions\":[\"仅输出 2025 年存在完成订单商品行的月份，不补齐无数据月份。\",\"收入采用语义层定义的净销售额：quantity * unit_price - discount_amount。\",\"若上月收入为 0，则该月 mom_pct 返回 NULL，以避免除零。\"]}",
  "reference_sql": "WITH monthly AS (SELECT strftime(order_date, '%Y-%m') AS month, SUM(total_amount) AS monthly_revenue FROM fact_orders WHERE status = 'completed' AND order_date >= DATE '2025-01-01' AND order_date < DATE '2026-01-01' GROUP BY month), lagged AS (SELECT month, monthly_revenue, LAG(monthly_revenue) OVER (ORDER BY month ASC) AS previous_revenue FROM monthly) SELECT month, monthly_revenue, ROUND((monthly_revenue - previous_revenue) / NULLIF(previous_revenue, 0) * 100, 2) AS mom_pct FROM lagged ORDER BY month ASC",
  "requested_model_id": "gpt-5.6-sol",
  "required_ast": [
    {
      "id": "mom-lag",
      "kind": "window_function",
      "min": 1,
      "name": "LAG",
      "order_by": [
        {
          "direction": "ASC",
          "expression": "month"
        }
      ],
      "partition_columns": []
    }
  ],
  "resolved_model_id": "gpt-5.6-sol",
  "result_preview": {
    "columns": [
      {
        "name": "month",
        "type": "VARCHAR"
      },
      {
        "name": "monthly_revenue",
        "type": "DECIMAL(38,2)"
      },
      {
        "name": "mom_pct",
        "type": "DOUBLE"
      }
    ],
    "extra": [],
    "missing": [],
    "row_count": 12,
    "rows": [
      [
        "2025-01",
        "41876.75",
        null
      ],
      [
        "2025-02",
        "31673.25",
        -24.37
      ],
      [
        "2025-03",
        "34373.25",
        8.52
      ],
      [
        "2025-04",
        "25069.00",
        -27.07
      ],
      [
        "2025-05",
        "30064.50",
        19.93
      ],
      [
        "2025-06",
        "31993.75",
        6.42
      ],
      [
        "2025-07",
        "36093.75",
        12.82
      ],
      [
        "2025-08",
        "29252.75",
        -18.95
      ],
      [
        "2025-09",
        "26246.25",
        -10.28
      ],
      [
        "2025-10",
        "21555.25",
        -17.87
      ],
      [
        "2025-11",
        "34944.25",
        62.11
      ],
      [
        "2025-12",
        "20373.00",
        -41.7
      ]
    ]
  },
  "run_id": 14,
  "score": {
    "ast_rules": [
      {
        "details": {
          "actual": 1,
          "required": 1
        },
        "id": "mom-lag",
        "kind": "window_function",
        "passed": true
      }
    ],
    "column_count": 5,
    "column_names": 5,
    "execution": 10,
    "ordering": 10,
    "protocol": 5,
    "read_only_ast": 5,
    "row_f1": 45,
    "sql_capability": 15,
    "total": 100
  },
  "stable_key": "monthly_mom_growth",
  "started_at": "2026-08-29T19:55:33.688980",
  "status": "completed",
  "suite_content_hash": "0a4a18b4374f510f5eff18b06272c30c3375e1f082ae405adc8ead7dd9c81556",
  "title": "月收入环比增长",
  "token_usage": {
    "cache_write_input_tokens": 0,
    "cached_input_tokens": 0,
    "input_tokens": 19138,
    "output_tokens": 402,
    "reasoning_output_tokens": 61
  },
  "visible_summary": "按月汇总 2025 年完成订单的净销售额，并使用 LAG 计算环比百分比；首个有收入月份为 NULL。"
}

原始案例 JSON ↗完整运行事件 JSONL ↗返回运行 #14